Human-machine Systems

Angesichts der zunehmenden strukturellen Verschaltung von Mensch und Maschine in der chirurgischen Praxis selbst genügt es nicht mehr, pathologische Veränderungen auf der Basis eines entsprechend theoriegeleiteten Bildwissensauf in medizinischen Visualisierung „lediglich“ zu erkennen. Bildkompetent müss ChirurgInnen inzwischen nicht mehr nur als DiagnostikerInnen sein, sondern Bilder gestalten zunehmend auch die Therapie. Visualisierungspraktiken lenken, steuern, führen und gestalten inwischen auch den Behandlungsprozess und etablieren ein verändertes Verhältnis zwischen ChirurgIn und PatientIn, zwischen Körper und Bild, zwischen Mensch und Maschine. Der Beitrag untersucht dieses Gefüge von Anschauung, Operativität und Bildlichkeit in der minimal-invasiven Chrirurgie anhand der medialen Produktionsbedingungen des roboter-assistierten Operationssystems Da Vinci. Dabei wird anhand konkreter Fallbeispiele der Architektur, Navigation und Steuerung des Systems gezeigt, dass dem Herstellerversprechen erhöhter medizinischer Effizienz und Präzision bildgeführter Operationssysteme eine praktische Kenntnis der Differenz zwischen Körper und Bild entgegenstehen muss, die nicht in Abrenzung zum Maschinellen verhandelt werden kann, sondern als Synthese von Chirurg und Operationssystem gedacht werden muss.

Even as progress in speech technologies and task and dialog modeling has allowed the development of advanced spoken dialog systems, the low-level interaction behavior of those systems remains often rigid and inefficient.

The goal of this thesis, is to provide a framework and models to endow spoken dialog systems with robust and flexible turn-taking abilities. To this end, we designed a new dialog system architecture that combines a high-level Dialog Manager (DM) with a low-level Interaction Manager (IM). While the DM operates on user and system turns, the IM operates at the sub-turn level, acting as the interface between the real time information of sensors and actuators, and the symbolic information of the DM. In addition, the IM controls reactive behavior, such as interrupting a system prompt when the user barges in. We propose two approaches to control turn-taking in the IM.

First, we designed an optimization method to dynamically set the pause duration threshold used to detect the end of user turns. Using a wide range of dialog features, this algorithm allowed us to reduce average system latency by as much as 22% over a fixed-threshold baseline, while keeping the detection error rate constant.

Second, we proposed a general, flexible model to control the turn-taking behavior of conversational agents. This model, the Finite-State Turn-Taking Machine (FSTTM), builds on previous work on 6-state representations of the conversational floor and extends them in two ways. First, it incorporates the notion of turn-taking action (such as grabbing or releasing the floor) and of state-dependent action cost. Second, it models the uncertainty that comes from imperfect recognition of user's turn-taking intentions. Experimental results show that this approach performs significantly better than the threshold optimization method for end-of-turn detection, with latencies up to 40% shorter than a fixed-threshold baseline. We also applied the FSTTM model to the problem of interruption detection, which reduced detection latency by 11% over a strong heuristic baseline.

The architecture as well as all the models proposed in this thesis were evaluated on the CMU Let's Go bus information system, a publicly available telephone-based dialog system that provides bus schedule information to the Pittsburgh population.

The current review addresses emerging issues that arise from the creation of safe, beneficial, and trusted artificial intelligence–air traffic controller (AI-ATCO) systems for air traffic management (ATM). These issues concern trust between the human user and automated or AI tools of interest, resilience, safety, and transparency. To tackle these issues, we advocate the development of practical AI-ATCO teaming frameworks by bringing together concepts and theories from neuroscience and explainable AI (XAI). By pooling together knowledge from both ATCO and AI perspectives, we seek to establish confidence in AI-enabled technologies for ATCOs. In this review, we present an overview of the extant studies that shed light on the research and development of trusted human-AI systems, and discuss the prospects of extending such works to building better trusted ATCO-AI systems. This paper contains three sections elucidating trust-related human performance, AI and explainable AI (XAI), and human-AI teaming. [COPYRIGHT CC BY-NC-ND 4.0, J. Y. ZHONG 2021, NANYANG TECHNOLOGICAL UNIVERSITY]

Human Machine Interface (HMI) concepts for autonomous vehicles have thus far been oriented towards the needs of the vehicle operator. In this work, an autonomous vehicle HMI utilizing LED lights, a display, and audio was created to communicate to others outside the vehicle. In the US, turn-taking at four-way stop sign intersections is typically negotiated via gesture or eye contact. In autonomous vehicles, there may not be an operator involved in the driving task to communicate this information. An HMI concept for this use case was built into a Wizard of Oz autonomous vehicle. Participants (N=64) interacted with the vehicle at an intersection as both a driver and as a pedestrian, after which they discussed their experiences in focus groups. HMI elements that communicate vehicle status or intentions concretely were better received than abstract indicators. Suggestions for design improvement and general implications for external HMI for autonomous vehicles are discussed.

Distributed Satellite Systems (DSS) provide a promising solution in increasing the sustainability of both the space and terrestrial environment through responsive Earth Observation (EO) and Space Domain Awareness (SDA) operations. To exploit the advantages of DSS mission architectures, a technical evolution is required from the deliberative methodologies of traditional ground station operations to approaches that are more suited to autonomous, reactive space mission architectures. At its core, this transition is directly reflected in the design, and development of new, more autonomous Mission Planning Systems that adopt the Adaptive Multi-Agent System (AMAS) framework. With a view towards trusted autonomy, this paper explores the required evolution towards a more supervisory role of future ground station operations. In doing so, this paper provides an initial analysis of a conceptual goal-based distributed space-based SDA application within the Observe Orient Decide and Act (OODA) decision loop framework.

With the proliferation of Unmanned Aircraft Systems (UAS) in low-altitude airspace and a growing interest in new Urban Air Mobility (UAM) solutions, the Air Traffic Controller (ATCo)'s responsibility to ensure safety and efficiency of operations can no longer be fulfilled with the conventional air traffic control paradigm. Hence, a new increasingly autonomous Decision Support System (DSS) specifically designed for integrated manned/UAS Traffic Management (UTM) is of paramount importance. This DSS makes use of advanced traffic flow and airspace management concepts, but to ensure effective teaming between the human and the system in challenging situations, the nature of their roles and responsibilities is to be analysed in depth and reflected in the design of suitable Human-Machine Interfaces and Interactions (HMI 2). The task analysis presented in this paper assessed the interdependencies between the human and the machine following the Observe-Orient-Decide-Act (OODA) framework. The paper focuses on the management of urban airspace, which is partitioned based on navigation performance. The human-machine workflow is presented and discussed, highlighting the proposed interactions in each subtask. To support closed-loop interactions and enhance system integrity, the UTM DSS makes use of the Cognitive HMI 2 concept, which is also briefly outlined in this paper.

What is it that differentiates man and puts him on the throne of the entire animal kingdom? Yes, it's the human brain, and not the human, which is the most valuable creation of God. But the brain, all its knowledge and power are destroyed after the death of man. Is it possible to model a brain and upload the contents of the real natural brain into it thereby propagating life even after death? Yes, indeed. Today, organ donation is giving a new lease of life to many ailing patients; however can brain be added to the list of organs that can be donated? Imagine the marvels that would be back into existence if we could replicate and restore the brains of geniuses like Sir Albert Einstein or Newton or even our great leaders of the past like Mahatma Gandhi. This paper presents a literature survey on the Blue Brain technology that promptly answers all these sparkling questions. Scientists today are in research to take artificial intelligence to a level beyond everything, to create a virtual brain that could think, react, make decisions and also keep everything in some form of memory to do everything that a normal human brain can. To achieve this, the main approach is to upload an actual brain in a virtual brain. So that even after death the person's conscience would be able to function exactly as a normal brain in the form of a machine. IBM along with scientists at BMI (Brain and Mind Institute) École Polytechnique Fédérale de Lausanne (EPFL) Research University in Switzerland are simulating the brain's biological systems into a 3D model, which would recreate the electrochemical interactions that take place inside the brain. If this simulation results in a success, the modeling would extend to different parts of the brain and make it function with all the abilities of a natural brain, thereby eliminating the chances of any brain malfunctions such as psychiatric disorders like depression and autism, which are possible in the normal brain. IBM names this project as the 'Blue Brain' project.

Adaptive Human-Machine Interfaces and Interactions (HMI2) are closed-loop cyber-physical systems comprising a network of sensors for measuring human, environmental and mission parameters, in conjunction with suitable software for adapting the HMI2 (command, control and display functions) in response to these real-time measurements. Cognitive HMI2 are a particular subclass of these systems, which support dynamic HMI2 adaptations based on the user's cognitive states. These states are estimated in real-time based on various neuro-physiological parameters from gaze, cardiorespiratory and brain activity measurements, which can be fused using suitable models. However, these measurements are affected by a variety of environmental factors and therefore their accuracy and precision need to be accurately characterised prior to operational use. This paper describes the characterisation activities performed on two types of eye tracking devices being used to support the development of cognitive human-machine systems. To classify the user's cognitive states, eye-tracking features are processed by a machine learning classifier based on fuzzy logic. This paper describes how the uncertainty associated with the classified outputs is quantified by propagating the uncertainty of the input features, through the classifier. This process is detailed in the paper due to its growing relevance because machine learning classifiers are now in common use.

The human-machine interface (HMI) is a crucial yet often overlooked aspect in the design of Unmanned Aircraft Systems (UASs). A properly designed HMI enhances situational awareness and reduces the workload of the ground pilot, thereby contributing to improving the overall mission performance. Typically, a Human Factors Engineering (HFE) program provides a methodological process to support good design. The program comprises three iterative stages: requirements analysis and capture, design and evaluation. A number of approaches can be adopted in the HFE program but given the wide range of applications and missions that are being undertaken by different types of UAS, it is advantageous to adopt a functional approach towards HMI design, where the HMI is designed around specific functions to be performed by either the human user or the system. The typical UAS functions include mission planning, sensor operation, data analysis and sense-and-avoid (SAA), and can also extend to multi-platform coordination and collaborative decision-making. The human factors considerations and the associated HMI elements supporting these functionalities are discussed.

The  Code  of  Practice  (CoP)  comprises  a  suitable ADAS  (Advanced  Driver  Assistance  System) description  concept  including ADAS  specific requirements  for  system  development. It  summarises best  practices  and  proposes  methods  for  risk assessment and controllability evaluation. The Code of Practice has been pro-duced  by  a  group  of  experts within  the  RESPONSE  3  project,  a subproject  of  the integrated  project  PReVENT,  a  European  automotive industry  activity,  co-funded  by  the  European Commission, to contribute to road safety by developing and demonstrating pre-ventive safety applications and technologies.

Digital photography has eclipsed its analog form, yet films cameras such as the Single Lens Reflex camera remain in use. This essay interrogates the status of the SLR camera in contemporary culture through a phenomenological lens to interrogate how, as a tool, it alters the user's relationship to the world. It then situates the SLR camera in the broader historical narrative of photographic technology and explores the contemporary relationship of the SLR camera to digital infrastructure. The essay proposes the notion of the " equipment-context " to refer to the broader cultural and institutional infrastructure that sustains SLR technology in the present environment. It contends that present interest in SLR cameras arises in context with an interest in film photography as a marginalized technology and aesthetic fetishization of the limited flexibility of older photographic cameras, and that the resuscitation of the SLR camera in contemporary culture brings it into dialogue with digital devices resulting in a hybrid of analog and digital.

Abstract
Psychrometry is concerned with the behavior of humid air and the prediction of its properties. More strictly it covers the behavior of any vapor (not just water vapor) when mixed with a gas (not just air). However, because the air/water system is of huge importance, not least to thermodynamic processes, and is the most commonly encountered gas/vapor mixture, the terminology employed often appears to be specific to air and water. Prediction of the properties of moist air, for example, humidity, maximum possible humidity, temperature, density and so on, is especially important in drying operations. The psychrometric chart is a simple graphical method of presenting this information, and the principles behind the chart are explained in chapter 1. The outcome of a drying process can often be followed more easily by monitoring the condition of the air with the aid of a psychrometric chart than by directly measuring the moisture content of the substance being dried.

This chapter is about managing sociotechnological risks. It is in the 70s that the notion of ‘high-risk’ (or ‘safety critical’) systems started to be distinguished and grouped into an independent category including industries such as the nuclear, aviation, marine, petrochemical or the railways. Any attempt such as this one to introduce this background in a few pages is necessarily restrictive, partly unfair but also a simplified account. And, there are of course many different strategies to do so. One option is to consider the field through the scientific disciplines involved, say sociology, engineering, psychology, ergonomics, management, etc. A second one, quite related to the first, is to introduce pioneers who, from different disciplinary backgrounds, produced seminal contributions used as shared references among various research communities interested in the safety of complex sociotechnological systems. A third one is to look into industry (aviation, nuclear or petrochemical) in order to illustrate and to differentiate the diversity of problems related to sociotechnological risks and how they materialise. Another option is to identify core concepts that sometimes cut across a range of disciplines, authors and industry which offers also good insights into the issues involved with sociotechnological risks. In any case, it is a very challenging task. The intention in this chapter is to combine a bit of these strategies in order to offer the reader a broad vision, and to follow editors’ guidelines specifying the following structure: first, key concepts, second, major debates and third open questions/perspectives.

Indem man die Maschine als in sich geschlossenes Gebilde konzipierte, wurde sie in einen unversöhnlichen Gegensatz zum “Menschlichen” gebracht. In diesem Text lege ich dar, dass ein Zusammendenken von Mensch und Maschine bereits vor über 350 Jahren dazu führte, dass das menschliche Selbstverständnis grundlegend infrage gestellt werden musste. Mit anderen Worten versuche ich nachzuvollziehen, was es bedeutet, sich den eigenen Körper als Maschine vorzustellen. Damit werfe ich einen neuen Blick auf den philosophiehistorischen Dualismus von Geist und Körper, der hier nicht hinsichtlich der Aufteilung von Vermögen wie Denken, Einbilden und Wahrnehmen befragt wird, sondern als ein Gebilde der Einbildungskraft und der philosophischen Methode verstanden werden kann, das sich in der Figur der beseelten Maschine konkretisiert.

Connecting the dots between discoveries in neuroscience (neuroplasticity), psychoneuroimmunology(the brain-immune loop) and user experience (gadget rub-off) indicate the nature of our time spent with gadgets is a vector in human health - mentally, socially and physically. The positive design of our interactions with devices therefore can have a positive impact on economy, civilization and society. Likewise, the absence of design that encourages positive interaction may encourage undesirable behaviors. Much like the architecture of physical spaces and buildings, the consequences of the architecture of the 21stcentury conversation between man and machine may last generations. AI and the Internet of Things are primary vectors for positive and negative impacts of technology.  We describe a growing body of co-discoveries occurring across a variety of disciplines that support the argument for human sciences in technology design.    The paper brings the rigors of science to bear on the humanities and makes the case for its relevance at this juncture in time to the design of technology involved in conversation and behaviors between humans and machines .

Situation awareness (SA) is an important constituent in human information processing and essential in pilots' decision-making processes. Acquiring and maintaining appropriate levels of SA is critical in aviation environments as it affects all decisions and actions taking place in flights and air traffic control. This paper provides an overview of recent measurement models and approaches to establishing and enhancing SA in aviation environments. Many aspects of SA are examined including the classification of SA techniques into six categories, and different theoretical SA models from individual, to shared or team, and to distributed or system levels. Quantitative and qualitative perspectives pertaining to SA methods and issues of SA for unmanned vehicles are also addressed. Furthermore, future research directions regarding SA assessment approaches are raised to deal with shortcomings of the existing state-of-the-art methods in the literature.

Resurgent interest in artificial intelligence (AI) techniques focused research attention
on their application in aviation systems including air traffic management (ATM), air traffic flow management (ATFM), and unmanned aerial systems traffic management (UTM). By considering a novel cognitive human–machine interface (HMI), configured via machine learning, we examined the requirements for such techniques to be deployed operationally in an ATM system, exploring aspects of vendor verification, regulatory certification, and end-user acceptance. We conclude that research into related fields such as explainable AI (XAI) and computer-aided verification needs to keep pace with applied AI research in order to close the research gaps that could inder operational deployment. Furthermore, we postulate that the increasing levels of automation and autonomy introduced by AI techniques will eventually subject ATM systems to certification requirements, and we propose a means by which ground-based ATM systems can be accommodated into the existing certification framework for aviation systems.

The debate on and around “killer robots” has been firmly established
at the crossroads of ethical, legal, political, strategic, and scientific discourses.
Flourishing at the two opposite poles, with a few contributors
caught in the middle, the polemic still falls short of a detailed, balanced,
and systematic analysis. It is for these reasons that we focus on
the nitty-gritties, multiple pros and cons, and implications of autonomous
weapon systems (AWS) for the prospects of the international
order. Moreover, a nuanced discussion needs to feature the considerations
of their technological continuity vs. novelty. The analysis begins
with properly delimiting the AWS category as fully autonomous
(lethal) weapon systems, capable of operating without human control
or supervision, including in dynamic and unstructured environments,
and capable of engaging in independent (lethal) decision-making,
targeting, and firing, including in an offensive manner. As its primary
goal, the article aims to move the existing debate to the level of a
first-order structure and offers its comprehensive operationalisation.
We propose an original framework based on a thorough analysis of
six specific dilemmas, and detailing the pro/con argument for each of
those: (1) (un)predictability of AWS performance; (2) dehumanization
of lethal decision-making; (3) depersonalisation of enemy (non-)combatant;
(4) human-machine nexus in coordinated operations; (5) strategic considerations; (6) AWS operation in law(less) zone. What follows are concluding remarks.

Keywords: autonomous weapon systems, killer robots, lethal decisionmaking,
military ethics, artificial intelligence, security regulation,
humanitarian law, revolution in military affairs, military strategy

Die Idee des »neuen Fleischs« durchkreuzt herkömmliche Grenzziehungen, welche die Domänen Natur und Technik klar voneinander unterscheiden. Was sagen uns die gleichermaßen verstörenden wieverführerischen Körperbilder in den Filmen David Cronenbergs über die Bewertung vonKulturtechnologien?Bettina Papenburg fokussiert in diesem Buch auf den grotesken Körperund eröffnet darüber einen frischen Blick auf Cronenbergs geladeneVisualisierungen von Körpermetaphern. Im Mittelpunkt der close readingsausgewählter Sequenzen aus den Filmen »The Brood«, »Crimes of theFuture«, »Videodrome«, »eXistenZ« und »Crash« stehen Darstellungen vonFragmentierung, Heterogenität und Exzess, sowie von Unschärfen undÜbergängen innerhalb unseres Kategoriensystems.

In  recent  years,  Home  Automation  systems  have seen rapid  changes  due  to  the  introduction of various  wireless technologies.  Zigbee is targeted  at  applications  that  require low data  rate,  long  battery  life,  and  secure  networking  and  has a  maximum  rate  of  250  kbits/s,  well  suited  for  periodic  or intermittent data  or  a single signal  transmission from  a sensor or input  device. This paper  discusses the design of a system that allows the user to interact  with it via his or her  voice in natural language  and  maps  user  utterances to  predefined  instructions, including  the  switching  of a  light  or  electrical  appliance.  The system is intended  to control  all lights and  electrical  appliances in a home or office using natural language. Having a comfortable learning  curve and being hands free by design, the system intends to make  home control  easier  and  more  convenient.

This paper presents an energy-optimal guidance and control strategy for 4-dimensional (4D) Trajectory-Based Operations (TBO) in the descent phase, supporting the development of 4D Human-Machine Interface (HMI) formats. The vertical guidance strategy uses multi-phase optimal control techniques based on point-mass aircraft dynamics to determine an energy-optimal descent profile fulfilling prescribed time constraints, additionally generating a set of control inputs which can be passed to the control module. The control strategy is decomposed into attitude and time-and-energy (T&E) components. The attitude control module corrects for cross-track deviations from the nominal profile previously calculated by the guidance algorithm, while the T&E control module corrects for the along-track distance and total energy deviations from the nominal profile. A virtual energy term is introduced which allows the control module to compensate for time deviations from the 4D trajectory. The proposed T&E guidance and control modules are verified through a number of representative case studies, showing that the proposed guidance and control modules allow the aircraft to follow a T&E-optimal 4D trajectory and to recover from deviations in the initial energy states. A prototype HMI is subsequently introduced to present the recommended control inputs to the pilot, also supporting assisted energy management in 4D descent operations.

Many remote airfields requires power for the lighting of airfield runway lights because power grid are not connected to the runway lights. It is challenging and necessary requirement to provide the adequate lighting facility. The findings of a Remote Airfield Lighting System research Centre gives a light with low power consumption and a color/intensity is obtained for identification of airfield and landing. This paper has added a new function along with the lights for the operational test with automatic switching of lights and batteries smart charging using solar panels with microcontroller and low cost pilot controlled lighting. The improvement is that RALS can be conveniently used at a low cost.

Computer-aided technologies (CAx) mean the use of computer technology to aid in the design, analysis and manufacture various products. International Journal of Computer-Aided technologies (IJCAx) is an open access, peer-reviewed journal that publishes articles which contribute new results in all areas of Computer Aided technologies such as CAD, CAM, CAIM,CAR, CARD, CASE etc. The journal focuses on all technical and practical aspects of Computer Aided technologies. The goal of this journal is to bring together researchers and practitioners from academia and industry to focus on advanced CAx tools and establishing new collaborations in these areas. Authors are solicited to contribute to this journal by submitting articles that illustrate research results, projects, surveying works and industrial experiences that describe significant advances in all Computer Aided technologies

A highly controversial entrance of Artificial Intelligence (AI) music generators in the world of music composition and performance is currently advancing. A fruitful research from Music Information Retrieval, Neural Networks and Deep Learning, among other areas, are shaping this future. Embodied and non-embodied AI systems have stepped into the world of jazz in order to co-create idiomatic music improvisations. But how musical these improvisations are? This dissertation looks at the resulted melodic improvisations produced by OMax, ImproteK and Djazz (OID) AI generators through the lens of the elements of music and it does so from a performer’s point of view. The analysis is based mainly on the evaluation of already published results as well as on a case study I carried out during the completion of this essay which includes performance, listening and evaluation of generated improvisations of OMax. The essay also reflects upon philosophical issues, cognitive foundations of emotion and meaning and provides a comprehensive analysis of the functionality of OID.

In 1996, Pablo Ventura turned his attention to the choreography software Life Forms to find out whether the then-revolutionary new tool could lead to new possibilities of expression in contemporary dance. During the next 2 decades, he devised choreographic techniques and custom software to create dance works that highlight the operational logic of computers, accompanied by computer-generated dance and media elements. This article provides a firsthand account of how Ventura's engagement with algorithmic concepts guided and transformed his choreographic practice. The text describes the methods that were developed to create computer-aided dance choreographies. Furthermore, the text illustrates how choreography techniques can be applied to correlate formal and aesthetic aspects of movement, music, and video. Finally, the text emphasizes how Ventura's interest in the wider conceptual context has led him to explore with choreographic means fundamental issues concerning the characteristics of humans and machines and their increasingly profound interdependencies. Keywords: computer-aided choreography, breaking of aesthetic and bodily habits, human– machine relationships, computer-generated and interactive media.

Advances in Unmanned Aerial Vehicles (UAV) autonomy have brought significant interest in multi-UAV operations, where a single operator commands and coordinates the tasks of multiple UAV. Multi-UAV surveillance applications over large geographic regions require human operators to process large amounts of information in order to make tactical decisions. To support the management of the human operator's workload and situational awareness, the concept of a ground control station utilising Cognitive Human-Machine Interfaces and Interactions (CHMI2) is presented. A CHMI2 module estimates the human operator's workload, fatigue and situational awareness in real-time to drive reconfigurations in the ground control station HMI2 , maximising the operator's situational awareness and decision-making for more effective mission management. A number of elements of the CHMI2 are presented in this paper, along with the concept of operations for separate scenarios involving littoral surveillance, as well as bushfire monitoring and fire-fighting.

Critique is directed against lingering philosophical Idealism and its counterpart; rationalistic physicalism. The remarkable discoveries of quantum physics invalidate them both, findings that have largely been ignored. The objective world constitutes of both mind and matter, and so does the subject. There exists no metaphysical barrier. Rather, subject and object are interactive and partake of the very same substance of reality. This has complementary nature, that is, manifests either as mind or matter.

Keywords: philosophy of color, theory of mind, ontology, epistemology, Idealism, Orch OR, qualia, reprentationism, artificial intelligence, AI, machine-human, physicalism, rationalism, complementarity, wave-particle duality, Kant, Descartes, Roger Penrose, James J. Gibson.

Whereas current aerospace Human-Machine Interfaces and Interactions (HMI2) are mostly static in their behaviour/appearance and require direct input from human operators, innovative HMI2 concepts are being proposed which allow for multimodal interactions or sense the functional state of human operators and dynamically adapt the level of automation. In particular, to facilitate trust between the human and machine, such systems need sensors that can reliably detect changes in the operator state. However, a number of environmental factors can affect the sensor's accuracy and precision. When used together with other novel sensors, eye tracking has a significant potential to enhance the adaptiveness of aerospace HMI2. This paper presents the activities carried out to quantify the uncertainty associated with eye tracking equipment available in the Avionics and Air Traffic Management (ATM) systems laboratory of RMIT University, which is being used to support the development of Cognitive HMI2. The presented methodology is used to characterise its measurement uncertainty based on a number of considerations, including the calibration error as well as gaze angle in static and dynamic conditions. The uncertainty associated with the eye tracker is used for error budgeting of a Cognitive HMI2 system which employs fuzzy logics to infer operator cognitive states based on eye tracking inputs.

E –learning is a method of learning that is delivered via electronic technology. Most of the E – Learning systems do not consider the individual aspects of the students ignoring the various requirements of  the learners. Personalization is widely used in various fields to provide users with more suitable and personalized service. Personalization of E – Learning system is a method of improving the existing learning system to satisfy the requirements of the different users / learners. Success of E- Leaning system rests on the effective usage of the system by the instructors and the student. This paper suggests a method for personalizing the E _ learning system using learner profile and sequential pattern mining based recommendation.

This work looks at improvisations produced by the OMax, ImproteK, and Djazz ML generators, through the lens of the elements of music and suggests a musically-oriented evaluation methodology. This idiomatic music analysis is presented from a jazz performer's point of view, reflecting upon cognitive foundations of emotion and meaning. The analysis, based mainly on the evaluation of already published material and on the authors' own experiments, shows musical drawbacks in terms of tension and release of the resulting melodic lines, voice leading of chords, rhythm, groove, dynamic control, and structure.

This article addresses the need for adaptive ethical analysis within machine learning that accounts for emerging problems concerning social bias and generative adversarial networks (gan s). I use John Dewey's criticisms of the reflex arc concept in psychology as a basis for understanding how these problems stem from human-gan interaction. By combining Dewey's criticisms with Donna Haraway's idea of cyborgs, Luciano Floridi's concept of distributed morality, and Shaowen Bardzell's recommendations for a feminist approach to human-computer interaction, I suggest a dynamic perspective from which to begin analyzing and solving issues of injustice evident in this particular domain of machine learning.

This essay argues for the designation of industrial and manufacturing machines as technologies of communication. Within communication scholarship, ICTs are synonymous with the word technology. Many of our theories regarding technology are based on human interaction with and through ICTs. However, ICTs are not the only technologies involved in communication. Drawing on scholarship from media studies, human-machine communication, and science and technology studies, I demonstrate how people’s interactions with “mute” technologies constitute communication. Industrial processes could not occur without the exchange of information between human and machine, and these industrial “rituals” between human and machine produce a particular reality for the worker and the organization. I argue that to understand communication in a machine culture in which people are constantly interacting with a variety of technologies, communication scholars must begin to study the multiplicity of machines and devices that are part of our lives.

Full issue: http://scholarworks.umass.edu/cpo/vol5/iss1/4

Предметом статьи является применение различных подходов к моделированию взаимодействия человека с системой при решении задач эргономической экспертизы. Выполнена классификация этих задач и известных методов моделирования взаимодействия (деятельности) человека с системой. На простом примере показаны возможности и ограничения структурных методов моделирования деятельности, таких как обобщенный структурный метод, метод иерархического и табличного анализа задач. Показано, что метод структурного функционального анализа обладает большим потенциалом при решении эргономических задач. Демонстрируется, что ослабление степени формализации метода позволяет решать в ходе экспертизы творческие задачи, однако при этом существенно повышает зависимость результатов от квалификации и опыта эргономиста или эксперта предметной области.

Advances in unmanned aircraft systems (UAS) have paved the way for progressively higher levels of intelligence and autonomy, supporting new modes of operation, such as the one-to-many (OTM) concept, where a single human operator is responsible for monitoring and coordinating the tasks of multiple unmanned aerial vehicles (UAVs). This paper presents the development and evaluation of cognitive human-machine interfaces and interactions (CHMI 2) supporting adaptive automation in OTM applications. A CHMI 2 system comprises a network of neurophysiological sensors and machine-learning based models for inferring user cognitive states, as well as the adaptation engine containing a set of transition logics for control/display functions and discrete autonomy levels. Models of the user's cognitive states are trained on past performance and neurophysiological data during an offline calibration phase, and subsequently used in the online adaptation phase for real-time inference of these cognitive states. To investigate adaptive automation in OTM applications, a scenario involving bushfire detection was developed where a single human operator is responsible for tasking multiple UAV platforms to search for and localize bushfires over a wide area. We present the architecture and design of the UAS simulation environment that was developed, together with various human-machine interface (HMI) formats and functions, to evaluate the CHMI 2 system's feasibility through human-in-the-loop (HITL) experiments. The CHMI 2 module was subsequently integrated into the simulation environment, providing the sensing, inference, and adaptation capabilities needed to realise adaptive automation. HITL experiments were performed to verify the CHMI 2 module's functionalities in the offline calibration and online adaptation phases. In particular, results from the online adaptation phase showed that the system was able to support real-time inference and human-machine interface and interaction (HMI 2) adaptation. However, the accuracy of the inferred workload was variable across the different participants (with a root mean squared error (RMSE) ranging from 0.2 to 0.6), partly due to the reduced number of neurophysiological features available as real-time inputs and also due to limited training stages in the offline calibration phase. To improve the performance of the system, future work will investigate the use of alternative machine learning techniques, additional neurophysiological input features, and a more extensive training stage.

Описывается постановка эксперимента для сбора данных о надежности выполнения оператором управляющих воздействий с помощью интерактивных элементов экрана. Воздействие состоит в выборе оборудования на мнемосхеме, указания его целевого состояния (открыть-закрыть, включить-отключить) и активации выполнения команды. Испытуемый выполняет четыре упражнения, отличающиеся наличием или отсутствием обратной связи о состоянии оборудования, а также наложением отвлекающих вопросов. В ходе эксперимента регистрируются физиологические показатели – частота сердечных сокращений, частота дыхания и электрическое сопротивление кожи. Предварительные оценки показывают вероятность безошибочной работы в случае обеспечения оператора информационной обратной связью 0,99–0,998.

Parmi les techniques appliquées au domaine de la Traitement Automatique du Langage Naturel TALN, on y trouve ceux appartenant à l'approche linguistique. Cette dernière tient en
considération les informations linguistiques liées au corpus de l'application visée. Ces informations nous aident à concevoir un système de compréhension d'énoncé dans un dialogue Homme-Machine. Pour atteindre un niveau de robustesse pour notre système, on prévoit l'ajout de quelques connaissances stochastiques à un certain niveau.